Guides¶
Practical guides for configuring, operating, and extending your synthetic organisation. Each guide is self-contained with a clear goal. Start with the Quickstart Tutorial if you are new to SynthOrg. Note: the platform, configuration surface, and the agent runtime that executes work are available today, exercised by deterministic e2e harnesses with a scripted provider; operator-facing maturity and real-provider acceptance are in active development (see the Roadmap).
New to SynthOrg?
Start with the Quickstart Tutorial to stand up the platform and configure a company in about 5 minutes.
-
Quickstart Tutorial
Install the CLI, pick a template, and stand up the platform in about 5 minutes.
-
Company Configuration
Complete YAML reference for every configuration option.
-
Agent Roles & Hierarchy
Define agents, seniority levels, personality, departments, and reporting lines.
-
Budget & Cost Control
Per-agent budgets, alert thresholds, auto-downgrade, and spending reports.
-
Security & Trust Policies
Trust strategies, autonomy levels, approval gates, and custom security policies.
-
Tool Integration (MCP)
Connect external tools via MCP servers with stdio or HTTP transports.
-
Deployment (Docker)
Run SynthOrg in production with Docker, hardening, and image verification.
-
Memory Configuration
Agent memory, shared org memory, retrieval pipeline, and consolidation.
-
Centralised Logging
Route structured logs to syslog, HTTP, OTLP, or external log aggregators.
-
Settings Reference
Resolve, view, and edit the 34 settings namespaces at runtime.
-
Notifications & Events
Configure notification sinks and subscribe to WebSocket event channels.
-
Workflow API Tutorial
curl tutorials for creating, versioning, activating, and executing workflows.
-
Agent Management
Hire, fire, promote, and customise agents through the REST API.
-
Human Interaction & API
REST + WebSocket API surface, rate limiting, RFC 9457 errors, Web UI features.
-
Contributing
Development workflow, testing, code style, and pull request process.
-
Adding a Provider
Configure LLM providers, models, and connection secrets.
-
Approval Workflow
Approve or reject parked agent actions through the API and dashboard.
-
A2A Federation
Federate agents across organisations with the agent-to-agent protocol.
-
Ceremony Scheduling Tuning
Tune sprint ceremonies, cadences, and scheduling strategies.
-
Cost Attribution
Attribute spend to agents, projects, and tasks for chargeback.
-
Custom MCP Server Development
Build your own MCP server to expose bespoke tools to agents.
-
Custom Rules & Meta-Loop
Author declarative signal rules that drive the self-improvement loop.
-
Dynamic Scoring
Configure candidate ranking and model-selection scoring strategies.
-
Fork Setup
Stand up your own fork with CI environments and required secrets.
-
Monitoring & Dashboards
Observe health, metrics, and live agent activity.
-
Ontology Extension
Define entity types and extend the semantic ontology.
-
Persistence Migrations
Manage schema revisions across the SQLite and Postgres backends.
-
REST API Examples
Copy-paste curl recipes for common REST API operations.
-
Webhook Management
Register, verify, and observe inbound and outbound webhooks.
-
Workers & Background Tasks
Run the worker pool and the background task queue.
-
Project Brain
Query a project's structured decision log: decisions, open questions, blockers, risks, dependencies, and plan revisions.
-
Living Documentation
Browse and search the per-project document wiki agents write to and retrieve from automatically.
-
Knowledge Substrate
Ingest external corpora (PDFs, web pages, repositories) into a provenance-tracked retrieval layer agents can cite.
-
:material-rudder:{ .lg .middle } Mid-Flight Steering
Inject hints and redirects into a running project and supersede obsolete tasks without stopping it.
-
Research Mode
Run recorded, replayable research briefs through a pipeline that synthesises cited reports.
-
Brownfield Intake
Import an existing codebase into a project, build a structure map, and run an automated analysis pass.